Multi-hop Reading Comprehension through Question Decomposition and Rescoring
Open paper
Benchmark
Model
Rank
Results
question-answering-on-hotpotqa
DecompRC
#18
JOINT-F1: 0.000
ANS-EM: 0.300
ANS-F1: 0.407
SUP-EM: 0.000
…
Rank counts only results with a code link.